mlsanityData to 7 Oct 2026

Mamba4Cast: Efficient Zero-Shot Time Series Forecasting with State Space Models

arXiv 2410.09385 ↗First posted 12 Oct 2024cs.LG cs.AIcited by 17

Not on the map. Why?

Abstract (arXiv)

This paper introduces Mamba4Cast, a zero-shot foundation model for time series forecasting. Based on the Mamba architecture and inspired by Prior-data Fitted Networks (PFNs), Mamba4Cast generalizes robustly across diverse time series tasks without the need for dataset specific fine-tuning. Mamba4Cast's key innovation lies in its ability to achieve strong zero-shot performance on real-world datasets while having much lower inference times than time series foundation models based on the transformer architecture. Trained solely on synthetic data, the model generates forecasts for entire horizons in a single pass, outpacing traditional auto-regressive approaches. Our experiments show that Mamba4Cast performs competitively against other state-of-the-art foundation models in various data sets while scaling significantly better with the prediction length. The source code can be accessed at https://github.com/automl/Mamba4Cast.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 31 of its 40 references that are in the map. First posted on arXiv 12 Oct 2024.

Builds on

31 of 40 references.

References · 31

  1. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  2. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  3. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,616
  4. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 1,981
  5. 2020Transformers are RNNs: Fast Autoregressive Transformers with Linear Attentioncited by 1,979
  6. 2022Are Transformers Effective for Time Series Forecasting?cited by 1,400
  7. 2024Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Dualitycited by 1,283
  8. 2022CoCa: Contrastive Captioners are Image-Text Foundation Modelscited by 1,265
  9. 2017DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networkscited by 1,004
  10. 2019N-BEATS: Neural basis expansion analysis for interpretable time series forecastingcited by 744
  11. 2024Chronos: Learning the Language of Time Seriescited by 712
  12. 2023Time-LLM: Time Series Forecasting by Reprogramming Large Language Modelscited by 680
19 more
  1. 2022TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Secondcited by 643
  2. 2018GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Accelerationcited by 603
  3. 2024Unified Training of Universal Time Series Forecasting Transformerscited by 588
  4. 2023Large Language Models Are Zero-Shot Time Series Forecasterscited by 491
  5. 2023Gated Linear Attention Transformers with Hardware-Efficient Trainingcited by 490
  6. 2024Parallelizing Linear Transformers with the Delta Rule over Sequence Lengthcited by 373
  7. 2021Transformers Can Do Bayesian Inferencecited by 338
  8. 2024xLSTM: Extended Long Short-Term Memorycited by 320
  9. 2024Is Mamba Effective for Time Series Forecasting?cited by 110
  10. 2024Can Mamba Learn How to Learn? A Comparative Study on In-Context Learning Taskscited by 104
  11. 2023ForecastPFN: Synthetically-Trained Zero-Shot Forecastingcited by 102
  12. 2024UniTS: A Unified Multi-Task Time Series Modelcited by 93
  13. 2020Meta-learning framework with applications to zero-shot time-series forecastingcited by 70
  14. 2024AutoTimes: Autoregressive Time Series Forecasters via Large Language Modelscited by 63
  15. 2023Contrast Everything: A Hierarchical Contrastive Framework for Medical Time-Seriescited by 59
  16. 2024Is Mamba Capable of In-Context Learning?cited by 45
  17. 2024MambaMixer: Efficient Selective State Space Models with Dual Token and Channel Selectioncited by 40
  18. 2023AutoGluon-TimeSeries: AutoML for Probabilistic Time Series Forecastingcited by 36
  19. 2023NetDiffus: Network Traffic Generation by Diffusion Models through Time-Series Imagingcited by 18

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 11; 2026: 6.

17 papers.

Sort:

By area:

  1. 2025Mantis: Lightweight Foundation Model for Time Series Classificationcited by 21
  2. 2025True Zero-Shot Inference of Dynamical Systems Preserving Long-Term Statisticscited by 20
  3. 2025Position: The Future of Bayesian Prediction Is Prior-Fittedcited by 19
  4. 2025TempoPFN: Synthetic Pre-training of Linear RNNs for Zero-shot Time Series Forecastingcited by 16
  5. 2026Reverso: Efficient Time Series Foundation Models for Zero-shot Forecastingcited by 11
  6. 2025Performance of Zero-Shot Time Series Foundation Models on Cloud Datacited by 10
  7. 2025Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancycited by 9
  8. 2025In-context Learning of Evolving Data Streams with Tabular Foundational Modelscited by 7
  9. 2025Unlocking Pretrained Vision Transformers for Time Series Classificationcited by 6
  10. 2026Foundation Inference Models for Ordinary Differential Equationscited by 3
  11. 2025Generative AI for Intent-Driven Network Management in 6G RAN: A Case Study on the Mamba Modelcited by 1
  12. 2025What Neuroscience Can Teach AI About Learning in Continuously Changing Environmentscited by 0
5 more
  1. 2025Foundation Model Forecasts: Form and Functioncited by 0
  2. 2026Prior-Fitted Functional Flow: In-Context Generative Models for Pharmacokineticscited by 0
  3. 2026FAME: Forecastability-Aware Mixture of Experts for Heterogeneous Time Series Forecastingcited by 0
  4. 2026A Minimal Interpretable Architecture for Zero-Shot Reconstruction of Dynamical Systemscited by 0
  5. 2026Continuous-Time Machine Learning: A Unified Mathematical Perspectivecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024A Mamba Foundation Model for Time Series Forecasting
  2. 2024SST: Multi-Scale Hybrid Mamba-Transformer Experts for Time Series Forecasting
  3. 2025ms-Mamba: Multi-scale Mamba for Time-Series Forecasting
  4. 2025DC-Mamber: A Dual Channel Prediction Model based on Mamba and Linear Transformer for Multivariate Time Series Forecasting
  5. 2024TimeMachine: A Time Series is Worth 4 Mambas for Long-term Forecasting
  6. 2024MambaTS: Improved Selective State Space Models for Long-term Time Series Forecasting
  7. 2024Bi-Mamba+: Bidirectional Mamba for Time Series Forecasting
  8. 2024Integration of Mamba and Transformer -- MAT for Long-Short Range Time Series Forecasting with Application to Weather Dynamics